Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-19 00:01:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

add extracted description/subject to pptParser

Browse Source
This commit is contained in:
reger 2015-02-22 05:31:56 +01:00
parent 8ec1db76ee
commit a0f04db9ea
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
source/net/yacy/document/parser/pptParser.java
View File

@ -29,7 +29,9 @@ package net.yacy.document.parser;
import java.io.BufferedInputStream;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import net.yacy.cora.document.id.AnchorURL;
import net.yacy.cora.util.CommonPattern;
@ -87,6 +89,10 @@ public class pptParser extends AbstractParser implements Parser {
keywlist = CommonPattern.COMMA.split(keywords);
} else keywlist = null;
final String subject = pptExtractor.getSummaryInformation().getSubject();
List<String> descriptions = new ArrayList<String>();
if (subject != null && !subject.isEmpty()) descriptions.add(subject);
/*
* create the plasmaParserDocument for the database
* and set shortText and bodyText properly
@ -102,7 +108,7 @@ public class pptParser extends AbstractParser implements Parser {
pptExtractor.getSummaryInformation().getAuthor(), // may be null
pptExtractor.getDocSummaryInformation().getCompany(),
null,
null,
descriptions,
0.0f, 0.0f,
contents,
null,